def transpose_to_marc21(record):
Mrecord=Record(force_utf8=True)
Mrecord.leader=record["_LEADER"]
for field in record:
if isint(field):
if int(field)<10:
if isinstance(record[field],list):
for elem in record[field]:
Mrecord.add_field(Field(tag=field,data=elem))
elif isinstance(record[field],str):
Mrecord.add_field(Field(tag=field,data=record[field]))
else:
for subfield in record[field]:
for ind, values in subfield.items():
indicators=[]
subfields=[]
for elem in values:
for k,v in elem.items():
if isinstance(v,str):
subfields.append(k)
subfields.append(v)
elif isinstance(v,list):
for subfield_elem in v:
subfields.append(k)
subfields.append(subfield_elem)
for elem in ind:
indicators.append(elem)
Mrecord.add_field(Field(tag=str(field),
indicators=indicators,
subfields=subfields))
return Mrecord.as_marc()
def create_record(cls,
work,
annotator,
force_create=False,
integration=None):
"""Build a complete MARC record for a given work."""
if callable(annotator):
annotator = annotator()
if isinstance(work, BaseMaterializedWork):
pool = work.license_pool
else:
pool = work.active_license_pool()
if not pool:
return None
edition = pool.presentation_edition
identifier = pool.identifier
_db = Session.object_session(work)
record = None
existing_record = getattr(work, annotator.marc_cache_field)
if existing_record and not force_create:
record = Record(data=existing_record.encode('utf-8'),
force_utf8=True)
if not record:
record = Record(leader=annotator.leader(work), force_utf8=True)
annotator.add_control_fields(record, identifier, pool, edition)
annotator.add_isbn(record, identifier)
# TODO: The 240 and 130 fields are for translated works, so they can be grouped even
# though they have different titles. We do not group editions of the same work in
# different languages, so we can't use those yet.
annotator.add_title(record, edition)
annotator.add_contributors(record, edition)
annotator.add_publisher(record, edition)
annotator.add_physical_description(record, edition)
annotator.add_audience(record, work)
annotator.add_series(record, edition)
annotator.add_system_details(record)
annotator.add_ebooks_subject(record)
data = record.as_marc()
if isinstance(work, BaseMaterializedWork):
setattr(pool.work, annotator.marc_cache_field, data)
else:
setattr(work, annotator.marc_cache_field, data)
# Add additional fields that should not be cached.
annotator.annotate_work_record(work, pool, edition, identifier, record,
integration)
return record
def create_record(cls, work, annotator, force_create=False, integration=None):
"""Build a complete MARC record for a given work."""
if callable(annotator):
annotator = annotator()
if isinstance(work, BaseMaterializedWork):
pool = work.license_pool
else:
pool = work.active_license_pool()
if not pool:
return None
edition = pool.presentation_edition
identifier = pool.identifier
_db = Session.object_session(work)
record = None
existing_record = getattr(work, annotator.marc_cache_field)
if existing_record and not force_create:
record = Record(data=existing_record.encode('utf-8'), force_utf8=True)
if not record:
record = Record(leader=annotator.leader(work), force_utf8=True)
annotator.add_control_fields(record, identifier, pool, edition)
annotator.add_isbn(record, identifier)
# TODO: The 240 and 130 fields are for translated works, so they can be grouped even
# though they have different titles. We do not group editions of the same work in
# different languages, so we can't use those yet.
annotator.add_title(record, edition)
annotator.add_contributors(record, edition)
annotator.add_publisher(record, edition)
annotator.add_physical_description(record, edition)
annotator.add_audience(record, work)
annotator.add_series(record, edition)
annotator.add_system_details(record)
annotator.add_ebooks_subject(record)
data = record.as_marc()
if isinstance(work, BaseMaterializedWork):
setattr(pool.work, annotator.marc_cache_field, data)
else:
setattr(work, annotator.marc_cache_field, data)
# Add additional fields that should not be cached.
annotator.annotate_work_record(work, pool, edition, identifier, record, integration)
return record
f = open('ostinos.csv')
csv_f = csv.reader(f)
out = open('osti_recs.csv', 'w')
data = csv.writer(out)
data.writerow([
'Title', 'Author', 'Date', 'Subjects', 'Description', 'OstiID', 'DOI',
'Report Number', 'DOE Number', 'URL', ''
])
marcOut = open('ostimarc.mrc', 'w')
dc = '{http://purl.org/dc/elements/1.1/}'
dcq = '{http://purl.org/dc/terms/}'
for number in csv_f:
ostiId = number[0]
marc = Record() # Create a new record for each loop.
tree = etree.parse('http://www.osti.gov/scitech/scitechxml?Identifier=' +
ostiId + '.xml')
for node in tree.iter():
if node.tag == dc + 'ostiId':
if node.text == ostiId:
o = node.getparent()
osti = o.getchildren()
getRecs(osti, data)
getMarc(osti, marc)
marcOut.write(marc.as_marc()) # Write each new record.
#-------------------------------------------------
f = open('ostinos.csv')
csv_f = csv.reader(f)
out = open ('osti_recs.csv', 'w')
data = csv.writer(out)
data.writerow(['Title', 'Author', 'Date', 'Subjects', 'Description', 'OstiID', 'DOI', 'Report Number', 'DOE Number', 'URL', ''])
marcOut = open('ostimarc.mrc', 'w')
dc = '{http://purl.org/dc/elements/1.1/}'
dcq = '{http://purl.org/dc/terms/}'
for number in csv_f:
ostiId = number[0]
marc = Record() # Create a new record for each loop.
tree = etree.parse('http://www.osti.gov/scitech/scitechxml?Identifier='+ ostiId+ '.xml')
for node in tree.iter():
if node.tag == dc + 'ostiId':
if node.text == ostiId:
o = node.getparent()
osti = o.getchildren()
getRecs(osti, data)
getMarc(osti, marc)
marcOut.write(marc.as_marc()) # Write each new record.
def json_to_marc(infilename, outfilename):
print('Processing: ' + infilename) #progress message
data = json.load(open(infilename, "r"))
record = Record(force_utf8=True) #create MARC record, enforce Unicode
# add fields 006, 007 and 008 with minimal physical information to every marc file
record.add_field(Field(tag='006', data="m"))
record.add_field(Field(tag='007', data="cr"))
# the iana language code from the json file is taken, checked against the list of language codes,
# substituted with its iso639-2 equivalent and put in position 21-24 of the field 008 content
field008val = " o 0eng d" # DEFAULT ENG
try:
if 'languages' in data and data['languages'][0] is not None:
field008val = field008val[0:21] + lang_map.get(
data['languages'][0], " ") + field008val[24:]
except IndexError:
field008val = field008val[0:21] + " " + field008val[24:]
record.add_field(Field(tag='008', data=field008val))
# extract issn, in json 'generic' and/or 'electronic', and put into separate subfields of 022
if "identifiers" in data and "issn" in data["identifiers"]:
field_issn = Field(tag='022', indicators=['0', '#'])
if "generic" in data["identifiers"]["issn"]:
field_issn.add_subfield('a',
data["identifiers"]["issn"]["generic"][0])
if "electronic" in data["identifiers"]["issn"]:
field_issn.add_subfield(
'l', data["identifiers"]["issn"]["electronic"][0])
record.add_field(field_issn)
# title of the series or journal
if data["is_part_of"] is not None and data["is_part_of"]['title_full']:
record.add_field(
Field(tag='245',
indicators=['0', '0'],
subfields=["a", data["is_part_of"]["title_full"][:9000]]))
if data["title"]:
record.add_field(
Field(tag='246',
indicators=['0', '0'],
subfields=["a", data["title"][:9000]]))
if data["year"]:
record.add_field(
Field(tag="260",
indicators=["#", "#"],
subfields=["c", data["year"]]))
# add field 506 to all records, as not present in all json files
record.add_field(
Field(tag='506', indicators=['0', '#'], subfields=["a",
"Open access"]))
# some json files contain a very long description; the maximum length of data in a variable field
#in MARC21 is 9,999 bytes, so here only a certain amount of content is put into the 520 field
if data["description"]:
record.add_field(
Field(tag='520',
indicators=['2', '#'],
subfields=["a", data["description"][:9000]]))
# keep together the journal url, host and domain as different subfields of field 856
# check if either exists, before initializing a new field instance
if data['url'] or (data['is_part_of'] is not None
and data['is_part_of']['url']):
field = Field(tag='856', indicators=['0', '0'])
if data['domain']:
field.add_subfield('a', data['domain'])
if data['is_part_of'] is not None and data['is_part_of']['url']:
field.add_subfield('d', data['is_part_of']['url'])
if data['url']:
field.add_subfield('u', data['url'])
record.add_field(field)
if data["volume"]:
record.add_field(
Field(tag='866',
indicators=['0', '0'],
subfields=["a", data["volume"]]))
#output marc file with same filename in Output directory
out = open(outfilename, 'wb')
out.write(record.as_marc())
out.close()
# execute function for creating separate records for subordinate resources
if data['subordinate_resources'] is not None:
subordinate_records = create_subordinate_records(
record, data['subordinate_resources'])
counter = 0
# add counter and "-sub" to filenames of subordinate records
for subordinate_record in subordinate_records:
out = open(
outfilename.replace(".marc", "-sub" + str(counter) + ".marc"),
'wb')
out.write(subordinate_record.as_marc())
out.close()
counter = counter + 1
notimpl = {}
records = {}
c = conn.cursor()
record = Record(file_encoding="utf-8", force_utf8=True)
record.myextra = {}
last = None
for l in c.execute('SELECT * FROM DBF_database_library_DAMEDB_dbf'):
if len(l.strip()) < 1:
if record.title():
log("**New record writing old one: ", record['001'], '\n',
'-' * 20)
with open('marcout.mrc', 'ab') as o:
o.write(record.as_marc())
records[record['001']] = record
record = Record(file_encoding="utf-8", force_utf8=True)
record.myextra = {}
pass
elif l.startswith("###"):
pass
elif l.startswith('M10'):
log("Urls have a non number therefore are extracted first")
record.add_field(
Field(tag='856', indicators=['4', '2'], subfields=['u', l[4:]]))
elif l.startswith('B03 '):
# TODO Lehrer/Schüler Bibliothek
pass
elif l.startswith('651i'):
# TODO Lehrer/Schüler Bibliothek
#-------------------------------------------------
f = open('ostinos2.csv')
csv_f = csv.reader(f)
out = open ('osti_recs2.csv', 'w')
data = csv.writer(out)
data.writerow(['Title', 'Author', 'Date', 'Subjects', 'Description', 'OstiID', 'DOI', 'Report Number', 'DOE Number', 'URL', ''])
marcOut = open('ostimarc.mrc', 'a')
dc = '{http://purl.org/dc/elements/1.1/}'
dcq = '{http://purl.org/dc/terms/}'
for number in csv_f:
ostiId = number[0]
marc = Record()
results = requests.get('http://www.osti.gov/scitech/scitechxml?Identifier="' + ostiId + '"')
tree = etree.fromstring(results.content)
for node in tree.iter():
if node.tag == dc + 'identifierReport':
#if node.text == ostiId:
o = node.getparent()
osti = o.getchildren()
getRecs(osti, data)
getMarc(osti, marc)
marcOut.write(marc.as_marc())
def main(arglist):
parser = argparse.ArgumentParser()
parser.add_argument('input', help='path to spreadsheet')
# parser.add_argument('output', help='save directory')
# parser.add_argument('--production', help='production DOIs', action='store_true')
args = parser.parse_args(arglist)
input = Path(args.input)
# Read spreadsheet
book_in = xlrd.open_workbook(str(input))
sheet = book_in.sheet_by_index(0) # get first sheet
col_headers = sheet.row_values(0)
# print(col_headers)
# print()
title_col = col_headers.index('Title')
subj_col = col_headers.index('Subject')
genre_col = col_headers.index('Genre')
pages_col = col_headers.index('Pages')
date_col = col_headers.index('Date')
pub_place_col = col_headers.index('Pub_Place')
publisher_col = col_headers.index('Publisher')
source_col = col_headers.index('Source')
writer_col = col_headers.index('Writer')
penciller_col = col_headers.index('Penciller')
inker_col = col_headers.index('Inker')
colorist_col = col_headers.index('Colorist')
letterer_col = col_headers.index('Letterer')
cover_artist_col = col_headers.index('Cover Artist')
editor_col = col_headers.index('Editor')
hist_note_col = col_headers.index('Historical Note')
note_col = col_headers.index('Note')
characters_col = col_headers.index('Characters')
story_arc_col = col_headers.index('Story Arc')
toc_col = col_headers.index('Table of Contents')
series_col = col_headers.index('Is Part of Series')
outmarc = open('records.mrc', 'wb')
# Boilerplate fields
field_ldr = '00000nam 2200000Ii 4500'
field_040 = Field(
tag='040',
indicators=[' ', ' '],
subfields=['a', 'VMC', 'b', 'eng', 'e', 'rda', 'c', 'VMC'])
field_049 = Field(tag='049',
indicators=[' ', ' '],
subfields=['a', 'VMCM'])
field_336_text = Field(
tag='336',
indicators=[' ', ' '],
subfields=['a', 'text', 'b', 'txt', '2', 'rdacontent'])
field_336_image = Field(
tag='336',
indicators=[' ', ' '],
subfields=['a', 'still image', 'b', 'sti', '2', 'rdacontent'])
field_337 = Field(tag='337',
indicators=[' ', ' '],
subfields=['a', 'unmediated', 'b', 'n', '2', 'rdamedia'])
field_338 = Field(tag='338',
indicators=[' ', ' '],
subfields=['a', 'volume', 'b', 'nc', '2', 'rdacarrier'])
field_380 = Field(tag='380',
indicators=[' ', ' '],
subfields=['a', 'Comic books and graphic novels.'])
field_506 = Field(
tag='506',
indicators=['1', ' '],
subfields=[
'a',
'Collection open to research. Researchers must register and agree to copyright and privacy laws before using this collection. Please contact Research Services staff before visiting the James Madison University Special Collections Library to use this collection.'
])
field_542 = Field(tag='542',
indicators=[' ', ' '],
subfields=[
'a', 'Copyright not evaluated', 'u',
'http://rightsstatements.org/vocab/CNE/1.0/'
])
field_588 = Field(
tag='588',
indicators=['0', ' '],
subfields=[
'a', 'Description based on indicia and Grand Comics Database.'
])
field_989 = Field(tag='989',
indicators=[' ', ' '],
subfields=['a', 'PN6728'])
for row in range(1, sheet.nrows):
print('Record ' + str(row))
title = sheet.cell(row, title_col).value
print(title)
lower_title = parse_title(lowercase_title(title))
title = parse_title(sheet.cell(row, title_col).value)
has_part_title = False
if len(title) == 3:
has_part_title = True
subj = sheet.cell(row, subj_col).value
subj = [x.strip() for x in subj.split(';')]
genre = sheet.cell(row, genre_col).value
genre = [x.strip() for x in genre.split(';')]
pages = sheet.cell(row, pages_col).value
date = sheet.cell(row, date_col).value[0:4]
pub_place = sheet.cell(row, pub_place_col).value
publisher = sheet.cell(row, publisher_col).value
source = sheet.cell(row, source_col).value
# writer = sheet.cell(row, writer_col).value
writer = []
if sheet.cell(row, writer_col).value:
writer = sheet.cell(row, writer_col).value
writer = [x.strip() for x in writer.split(';')]
penciller = []
if sheet.cell(row, penciller_col).value:
penciller = sheet.cell(row, penciller_col).value
penciller = [x.strip() for x in penciller.split(';')]
inker = []
if sheet.cell(row, inker_col).value:
inker = sheet.cell(row, inker_col).value
inker = [x.strip() for x in inker.split(';')]
colorist = []
if sheet.cell(row, colorist_col).value:
colorist = sheet.cell(row, colorist_col).value
# print(colorist)
# print('COLORIST FROM SHEET=' + colorist + '=END')
# print(bool(colorist))
colorist = [x.strip() for x in colorist.split(';')]
letterer = []
if sheet.cell(row, letterer_col).value:
letterer = sheet.cell(row, letterer_col).value
letterer = [x.strip() for x in letterer.split(';')]
cover_artist = []
if sheet.cell(row, cover_artist_col).value:
cover_artist = sheet.cell(row, cover_artist_col).value
cover_artist = [x.strip() for x in cover_artist.split(';')]
editor = []
if sheet.cell(row, editor_col).value:
editor = sheet.cell(row, editor_col).value
editor = [x.strip() for x in editor.split(';')]
hist_note = []
if sheet.cell(row, hist_note_col).value:
hist_note = sheet.cell(row, hist_note_col).value
note = []
if sheet.cell(row, note_col).value:
note = sheet.cell(row, note_col).value
characters = []
if sheet.cell(row, characters_col).value:
characters = sheet.cell(row, characters_col).value
characters = [x.strip() for x in characters.split(';')]
story_arc = []
if sheet.cell(row, story_arc_col).value:
story_arc = sheet.cell(row, story_arc_col).value
toc = []
if sheet.cell(row, toc_col).value:
toc = sheet.cell(row, toc_col).value
series = sheet.cell(row, series_col).value
# print(cover_artist)
# print(characters)
# print(writer)
# print(subfields_from_string(writer[0]))
# print(name_direct_order(subfields_from_string(writer[0])[1]))
# print(title)
# print(parse_title(title))
record = Record()
# Add boilerplate fields
record.leader = field_ldr
record.add_ordered_field(field_040)
record.add_ordered_field(field_049)
record.add_ordered_field(field_336_text)
record.add_ordered_field(field_336_image)
record.add_ordered_field(field_337)
record.add_ordered_field(field_338)
record.add_ordered_field(field_380)
record.add_ordered_field(field_506)
record.add_ordered_field(field_542)
record.add_ordered_field(field_588)
record.add_ordered_field(field_989)
# Add other fields
today = datetime.today().strftime('%y%m%d')
data_008 = today + 't' + date + date + 'xx a 6 000 1 eng d'
field_008 = Field(tag='008', data=data_008)
record.add_ordered_field(field_008)
subfields_099 = []
if has_part_title:
subfields_099 = ['a', title[0] + ': ' + title[1], 'a', title[2]]
else:
subfields_099 = ['a', title[0], 'a', title[1]]
field_099 = Field(tag='099',
indicators=[' ', '9'],
subfields=subfields_099)
record.add_ordered_field(field_099)
if writer:
# Add 100 for first writer
subfield_content = subfields_from_string_relator(
writer[0], 'writer')
field_100 = Field(tag='100',
indicators=['1', ' '],
subfields=subfield_content)
record.add_ordered_field(field_100)
# Multiple writers
if len(writer) > 1:
# Add 700s for all writers after the first
for i in writer[1:]:
subfield_content = subfields_from_string_relator(
i, 'writer')
field_700 = Field(tag='700',
indicators=['1', ' '],
subfields=subfield_content)
record.add_ordered_field(field_700)
if writer:
f245_ind1 = 1
else:
f245_ind1 = 0
f245_ind2 = 0
if str.startswith(title[0], 'The '):
f245_ind2 = 4
elif str.startswith(title[0], 'An '):
f245_ind2 = 3
elif str.startswith(title[0], 'A '):
f245_ind2 = 2
subfields_245 = []
if has_part_title:
subfields_245 = [
'a', title[0] + '.', 'p', title[1] + ',', 'n', title[2]
]
else:
subfields_245 = ['a', title[0] + ',', 'n', title[1]]
# If writer exists, add $c
if writer:
subfields_245[-1] = subfields_245[-1] + ' /'
subfields_245.append('c')
subfields_245.append(
name_direct_order(subfields_from_string(writer[0])[1]) +
', writer.')
else:
# If no writer, add 245 ending punctuation
subfields_245[-1] = subfields_245[-1] + '.'
field_245 = Field(tag='245',
indicators=[f245_ind1, f245_ind2],
subfields=subfields_245)
record.add_ordered_field(field_245)
field_264_1 = Field(tag='264',
indicators=[' ', '1'],
subfields=[
'a', pub_place + ' :', 'b', publisher + ',',
'c', date + '.'
])
record.add_ordered_field(field_264_1)
field_264_4 = Field(tag='264',
indicators=[' ', '4'],
subfields=['c', '©' + date])
record.add_ordered_field(field_264_4)
field_300 = Field(tag='300',
indicators=[' ', ' '],
subfields=[
'a', pages + ' pages :', 'b',
'chiefly color illustrations.'
])
record.add_ordered_field(field_300)
subfields_490 = []
if has_part_title:
subfields_490 = [
'a', lower_title[0] + '. ' + lower_title[1] + ' ;', 'v',
lower_title[2]
]
else:
subfields_490 = ['a', lower_title[0] + ' ;', 'v', lower_title[1]]
field_490 = Field(tag='490',
indicators=['1', ' '],
subfields=subfields_490)
record.add_ordered_field(field_490)
if hist_note:
field_500_hist = Field(tag='500',
indicators=[' ', ' '],
subfields=['a', hist_note + '.'])
record.add_ordered_field(field_500_hist)
if note:
field_500_note = Field(tag='500',
indicators=[' ', ' '],
subfields=['a', note + '.'])
record.add_ordered_field(field_500_note)
if toc:
if not toc.endswith('.') and not toc.endswith(
'?') and not toc.endswith('!'):
toc += '.'
field_505 = Field(tag='505',
indicators=['0', ' '],
subfields=['a', toc])
record.add_ordered_field(field_505)
if story_arc:
field_520 = Field(tag='520',
indicators=[' ', ' '],
subfields=[
'a', '"' + story_arc +
'" -- Grand Comics Database.'
])
record.add_ordered_field(field_520)
field_561 = Field(tag='561',
indicators=[' ', ' '],
subfields=['a', source + '.'])
record.add_ordered_field(field_561)
for i in subj:
if not i.endswith('.') and not i.endswith(')'):
i += '.'
field_650 = Field(tag='650',
indicators=[' ', '0'],
subfields=['a', i])
record.add_ordered_field(field_650)
for i in genre:
if not i.endswith('.') and not i.endswith(')'):
i += '.'
field_655 = Field(tag='655',
indicators=[' ', '7'],
subfields=['a', i, '2', 'lcgft'])
record.add_ordered_field(field_655)
if characters:
# print(characters)
subfield_content = 'Characters: '
for i in characters[:-1]:
subfield_content += i + '; '
subfield_content += characters[-1] + '.'
field_500 = Field(tag='500',
indicators=[' ', ' '],
subfields=['a', subfield_content])
record.add_ordered_field(field_500)
# Create 600 and 650 for "Fictitious character" entries
# TODO check for existing 650 and don't add if a duplicate
if any('Fictitious character' in c for c in characters):
fic_chars = [
c for c in characters if 'Fictitious character' in c
]
for i in fic_chars:
fic_char_name = re.sub(
r'^(.*?) (\(Fictitious character.*\))$', r'\g<1>', i)
fic_char_c = re.sub(
r'^(.*?) (\(Fictitious character.*\))$', r'\g<2>', i)
field_600 = Field(
tag='600',
indicators=['0', '0'],
subfields=['a', fic_char_name, 'c', fic_char_c])
record.add_ordered_field(field_600)
field_650 = Field(tag='650',
indicators=[' ', '0'],
subfields=['a', i])
record.add_ordered_field(field_650)
if penciller:
for i in penciller:
subfield_content = subfields_from_string_relator(
i, 'penciller')
field_700 = Field(tag='700',
indicators=['1', ' '],
subfields=subfield_content)
record.add_ordered_field(field_700)
if inker:
for i in inker:
subfield_content = subfields_from_string_relator(i, 'inker')
field_700 = Field(tag='700',
indicators=['1', ' '],
subfields=subfield_content)
record.add_ordered_field(field_700)
if colorist:
for i in colorist:
subfield_content = subfields_from_string_relator(i, 'colorist')
field_700 = Field(tag='700',
indicators=['1', ' '],
subfields=subfield_content)
record.add_ordered_field(field_700)
if letterer:
for i in letterer:
subfield_content = subfields_from_string_relator(i, 'letterer')
field_700 = Field(tag='700',
indicators=['1', ' '],
subfields=subfield_content)
record.add_ordered_field(field_700)
if cover_artist:
for i in cover_artist:
subfield_content = subfields_from_string_relator(
i, 'cover artist')
field_700 = Field(tag='700',
indicators=['1', ' '],
subfields=subfield_content)
record.add_ordered_field(field_700)
if editor:
for i in editor:
subfield_content = subfields_from_string_relator(i, 'editor')
field_700 = Field(tag='700',
indicators=['1', ' '],
subfields=subfield_content)
record.add_ordered_field(field_700)
# field_700 = Field(tag = '700',
# indicators = ['7',' '],
# subfields = [
# 'a', doi,
# '2', 'doi'])
subfields_773 = subfields_from_string(series)
field_773 = Field(tag='773',
indicators=['0', '8'],
subfields=subfields_773)
record.add_ordered_field(field_773)
subfields_830 = []
if has_part_title:
subfields_830 = [
'a', lower_title[0] + '.', 'p', lower_title[1] + ' ;', 'v',
lower_title[2] + '.'
]
else:
subfields_830 = [
'a', lower_title[0] + ' ;', 'v', lower_title[1] + '.'
]
field_830 = Field(tag='830',
indicators=[' ', '0'],
subfields=subfields_830)
record.add_ordered_field(field_830)
outmarc.write(record.as_marc())
print()
outmarc.close()
out = open('osti_recs.csv', 'w')
data = csv.writer(out)
data.writerow([
'Title', 'Author', 'Date', 'Subjects', 'Description', 'OstiID', 'DOI',
'Report Number', 'DOE Number', 'URL', ''
])
marcOut = open('ostimarc.mrc', 'w')
marc = Record()
dc = '{http://purl.org/dc/elements/1.1/}'
dcq = '{http://purl.org/dc/terms/}'
for number in csv_f:
ostiId = number[0]
results = requests.get(
'http://www.osti.gov/scitech/scitechxml?Identifier=' + ostiId)
tree = etree.fromstring(results.content)
for node in tree.iter():
if node.tag == dc + 'ostiId':
if node.text == ostiId:
o = node.getparent()
osti = o.getchildren()
getRecs(osti)
getMarc(osti)
continue
marcOut.write(marc.as_marc())
def to_marc(obj):
primary_author = format_author(obj['z_authors'][0],
reverse=True) if obj['z_authors'] else None
split_title = [part.strip() for part in title_splitter.split(obj['title'])]
if len(split_title) > 2:
primary_title = f'{split_title[0]} {split_title[1]}'
remainder_of_title = f'{" ".join(split_title[2:])} /'
else:
primary_title = f'{" ".join(split_title)} /'
remainder_of_title = ''
record = Record()
record.leader.type_of_record = 'a'
record.leader.coding_scheme = 'a'
record.bibliographic_level = 'm'
record.cataloging_form = 'a'
# record.add_field(Field(
# tag = '041',
# indicators = ['#', '#'],
# subfields = [
# 'a', 'Eng'
# ]))
if primary_author:
record.add_field(
Field(tag='100',
indicators=['0', ' '],
subfields=['a', primary_author]))
if remainder_of_title:
record.add_field(
Field(tag='245',
indicators=['0', '0'],
subfields=[
'a', primary_title, 'b', remainder_of_title, 'c',
format_authors(obj['z_authors'])
]))
else:
record.add_field(
Field(tag='245',
indicators=['0', '0'],
subfields=[
'a', f"{obj['title']} /", 'c',
format_authors(obj['z_authors'])
]))
record.add_field(
Field(tag='260',
indicators=[' ', ' '],
subfields=['b', obj['publisher'], 'c',
str(obj['year'])]))
record.add_field(
Field(tag='500',
indicators=[' ', ' '],
subfields=[
'a',
f"Article from {obj['journal_name']}.",
]))
record.add_field(
Field(tag='856',
indicators=['4', '0'],
subfields=[
'u', obj['best_oa_location']['url'], 'y',
'View article as PDF'
]))
record.add_field(
Field(tag='856',
indicators=[' ', ' '],
subfields=['u', obj['doi_url'], 'y', 'DOI']))
# print(str(record))
return record.as_marc()
def output_to_marc(output_text, doc_year, doc_num, non_filing, doc_title,
doc_iss_year, num_pages, welcomes, this_res, date_field_008,
time_field_590, field_710, time_field_856, url_entry):
'''
Outputs data in MARC format via PyMARC. Field 999 includes a random number
generator to get around the problem of the LMS needing unique item ids.
'''
record = Record()
record.add_field(Field(
tag='000',
data='im 0c',
))
record.add_field(
Field(
tag='008',
data=f'{date_field_008}n 000 0 eng u',
))
record.add_field(
Field(tag='080',
indicators=[' ', ' '],
subfields=[
'a',
f'657 {doc_year}{doc_num}',
]))
record.add_field(
Field(tag='110', indicators=['2', ' '], subfields=[
'a',
'COMPANY',
]))
record.add_field(
Field(tag='245',
indicators=['1', f'{str(non_filing)}'],
subfields=[
'a',
f'{doc_title}',
]))
record.add_field(
Field(tag='260',
indicators=[' ', ' '],
subfields=[
'a',
'London : ',
'b',
'COMPANY, ',
'c',
f'{doc_iss_year}',
]))
record.add_field(
Field(tag='300',
indicators=[' ', ' '],
subfields=[
'a',
f'{str(num_pages)} pages',
]))
record.add_field(
Field(tag='336',
indicators=[' ', ' '],
subfields=[
'a',
'text |2rdacontent',
]))
record.add_field(
Field(tag='337',
indicators=[' ', ' '],
subfields=[
'a',
'unmediated |2rdamedia',
]))
record.add_field(
Field(tag='338',
indicators=[' ', ' '],
subfields=[
'a',
'volume |2rdacarrier',
]))
record.add_field(
Field(tag='490',
indicators=[' ', ' '],
subfields=[
'a',
'COMPANY ; ',
'v',
f'{doc_num}/{doc_year}',
]))
record.add_field(
Field(tag='500',
indicators=[' ', ' '],
subfields=[
'a',
f'"{welcomes}... {this_res}"',
]))
record.add_field(
Field(tag='590',
indicators=[' ', ' '],
subfields=[
'a',
f'{time_field_590}',
]))
record.add_field(
Field(tag='650', indicators=[' ', ' '], subfields=[
'a',
'',
]))
record.add_field(
Field(tag='650', indicators=[' ', ' '], subfields=[
'a',
'',
]))
record.add_field(
Field(tag='710',
indicators=['2', ' '],
subfields=[
'a',
f'{field_710}',
]))
record.add_field(
Field(tag='710', indicators=['2', ' '], subfields=[
'a',
'COMPANY',
]))
record.add_field(
Field(tag='830', indicators=[' ', ' '], subfields=[
'a',
'COMPANY',
]))
record.add_field(
Field(tag='856',
indicators=[' ', ' '],
subfields=[
'a',
f'In {time_field_856} available at : ',
'u',
f'{url_entry}',
]))
record.add_field(
Field(tag='999',
indicators=[' ', ' '],
subfields=[
'a',
f'087 {doc_year}{doc_num}',
'w',
'UDC',
'c',
'1',
'i',
f'{random.randint(1000000000,9999999999)}',
'l',
'STORE',
'm',
'COMPANY-LIB',
'r',
'Y',
's',
'Y',
't',
'REFERENCE',
]))
record.add_field(
Field(tag='999',
indicators=[' ', ' '],
subfields=[
'a',
f'657 {doc_year}{doc_num}',
'w',
'UDC',
'c',
'1',
'i',
f'{random.randint(1000000000,9999999999)}',
'l',
'STORE',
'm',
'COMPANY-LIB',
'r',
'Y',
's',
'Y',
't',
'LENDING',
]))
# Write MARC file to disk.
with open(f'.\\marc_files\\marc_{doc_year}-{doc_num}.mrc', 'wb') as out:
out.write(record.as_marc())
def main(arglist):
parser = argparse.ArgumentParser()
parser.add_argument('setname',
help='bepress collection setname (e.g., diss201019)')
parser.add_argument(
'input',
help=
'path to bepress spreadsheet (containing DOIs) in "Excel 97-2003 Workbook (.xls)" format'
)
# parser.add_argument('output', help='save directory')
# parser.add_argument('--production', help='production DOIs', action='store_true')
args = parser.parse_args(arglist)
# Read config file and parse setnames into lists by category
config = configparser.ConfigParser(allow_no_value=True)
config.read('local_settings.ini')
etd_setnames = []
for i in config.items('ETD'):
etd_setnames.append(i[0])
# Add additional categories here
setname = args.setname
input = Path(args.input)
# jsonmerge setup
schema = {"properties": {"entries": {"mergeStrategy": "append"}}}
merger = Merger(schema)
# Timestamp output
date_time = datetime.now().strftime('%Y-%m-%d %H:%M:%S')
print(date_time)
print()
print('------------------------------------------------------------')
print('------------------------------------------------------------')
# Read Bepress spreadsheet
# TODO check that setname matches spreadsheet?
# print()
# print('Reading spreadsheet...')
book_in = xlrd.open_workbook(str(input))
sheet1 = book_in.sheet_by_index(0) # get first sheet
# sheet1_name = book_in.sheet_names()[0] # name of first sheet
sheet1_col_headers = sheet1.row_values(0)
try:
doi_col_index = sheet1_col_headers.index('doi')
except ValueError:
print('DOI field not found in bepress metadata')
url_col_index = sheet1_col_headers.index('calc_url')
# Read URLs and DOIs from spreadsheet
bepress_data = {}
for row in range(1, sheet1.nrows):
bepress_url = sheet1.cell(row, url_col_index).value
bepress_doi = sheet1.cell(row, doi_col_index).value
bepress_data[bepress_url] = bepress_doi
print(bepress_data)
# Read query criteria from file, inserting setname and starting bib number
with open('query_setname_no_doi_bib_limiter.json', 'r') as file:
data = file.read().replace('SETNAME',
setname).replace('bxxxxxxx', 'b1000000')
# print(data)
# Authenticate to get token, using Client Credentials Grant https://techdocs.iii.com/sierraapi/Content/zReference/authClient.htm
key_secret = config.get('Sierra API', 'key') + ':' + config.get(
'Sierra API', 'secret')
key_secret_encoded = base64.b64encode(
key_secret.encode('UTF-8')).decode('UTF-8')
headers = {
'Authorization': 'Basic ' + key_secret_encoded,
'Content-Type': 'application/x-www-form-urlencoded'
}
response = requests.request(
'POST',
'https://catalog.lib.jmu.edu/iii/sierra-api/v5/token',
headers=headers)
j = response.json()
token = j['access_token']
auth = 'Bearer ' + token
headers = {'Accept': 'application/json', 'Authorization': auth}
# Search Sierra for records with URL+setname and no DOI in 024 field
limit = 2000
response = requests.request(
'POST',
'https://catalog.lib.jmu.edu/iii/sierra-api/v5/bibs/query?offset=0&limit='
+ str(limit),
headers=headers,
data=data)
# print(response.text)
j = response.json()
records_returned = j['total']
# print('Records returned:', j['total'])
j_all = j
if j['total'] == 0:
print('No ' + setname + ' records in Sierra are missing DOIs')
else:
# If limit was reached, repeat until all record IDs are retrieved
while j['total'] == limit:
# print('--------------------------------')
last_record_id = j['entries'][-1:][0]['link'].replace(
'https://catalog.lib.jmu.edu/iii/sierra-api/v5/bibs/', '')
# print('id of last record returned:', last_record_id)
next_record_id = str(int(last_record_id) + 1)
# print('id of starting record for next query:', next_record_id)
# Read query criteria from file, inserting setname
with open('query_setname_no_doi_bib_limiter.json', 'r') as file:
data = file.read().replace('SETNAME', setname).replace(
'bxxxxxxx', 'b' + next_record_id)
response = requests.request(
'POST',
'https://catalog.lib.jmu.edu/iii/sierra-api/v5/bibs/query?offset=0&limit='
+ str(limit),
headers=headers,
data=data)
j = response.json()
records_returned += j['total']
print('Found ' + records_returned + ' ' + setname +
' Sierra records that are missing DOIs')
# print(response.text)
# Add new response to previous ones
j_all = merger.merge(j_all, j)
j_all['total'] = records_returned
# print(j_all)
# Put bib IDs in list
bib_id_list = []
for i in j_all['entries']:
bib_id = i['link'].replace(
'https://catalog.lib.jmu.edu/iii/sierra-api/v5/bibs/', '')
bib_id_list.append(bib_id)
# print(bib_id_list)
# Get bib varField info for all records, 500 bib IDs at a time
fields = 'varFields'
#querystring = {'id':'3323145', 'fields':fields}
j_data_all = {}
records_returned_data = 0
chunk_size = 499
for i in range(0, len(bib_id_list), chunk_size):
bib_id_list_partial = bib_id_list[i:i + chunk_size]
querystring = {
'id': ','.join(bib_id_list_partial),
'fields': fields,
'limit': limit
}
response = requests.request(
'GET',
'https://catalog.lib.jmu.edu/iii/sierra-api/v5/bibs/',
headers=headers,
params=querystring)
j_data = response.json()
records_returned_data += j_data['total']
j_data_all = merger.merge(j_data_all, j_data)
j_data_all['total'] = records_returned_data
# Parse varField data for OCLC number and URL
sierra_data = {}
for i in j_data_all['entries']:
id = i['id']
var_fields = i['varFields']
sierra_url = ''
for v in var_fields:
if 'marcTag' in v:
if '001' in v['marcTag']:
oclc_num = v['content']
if '856' in v['marcTag']:
for s in v['subfields']:
if 'u' in s['tag']:
if 'commons.lib.jmu.edu' in s['content']:
if sierra_url:
sierra_url += ';'
sierra_url += s['content']
# Turn bib id into bib number
bib_reversed = id[::-1]
total = 0
for i, digit, in enumerate(bib_reversed):
prod = (i + 2) * int(digit)
total += prod
checkdigit = total % 11
if checkdigit == 10:
checkdigit = 'x'
bib_num = 'b' + id + str(checkdigit)
# print(bib_num)
# print('OCLC number:', oclc_num)
# print('URL:', sierra_url)
# print()
sierra_data[bib_num] = (oclc_num, sierra_url)
print(sierra_data)
# Create short MARC records with bib number and DOI fields, and create spreadsheet with OCLC numbers and DOI fields
outmarc = open('shortrecs.mrc', 'wb')
outtext = open('searchkeys.txt', 'w')
outbook = xlwt.Workbook()
outsheet = outbook.add_sheet('Sheet 1')
col_headers = ['OCLC Number', 'Bib Number', '024', '856']
for x, y in enumerate(col_headers, 0):
outsheet.write(0, x, y)
outbook.save('OCLC Changes.xls')
for i, j in enumerate(sierra_data, 1):
print(i)
print(j)
# Get DOI from spreadsheet data
doi_url = bepress_data[sierra_data[j][1]]
print(doi_url)
doi = doi_url.replace('https://doi.org/', '')
spreadsheet_024 = '7\$a' + doi + '$2doi'
#spreadsheet_856 = '40$zFull-text of dissertation on the Internet$u' + doi_url
# Get OCLC number
oclcnum = sierra_data[j][0]
field_907 = Field(tag='907',
indicators=[' ', ' '],
subfields=['a', '.' + j])
field_024 = Field(tag='024',
indicators=['7', ' '],
subfields=['a', doi, '2', 'doi'])
field_856 = Field(tag='856',
indicators=['4', '0'],
subfields=[
'z',
'Full-text of dissertation on the Internet',
'u', doi_url
])
field_506_1 = Field(
tag='506',
indicators=['0', ' '],
subfields=[
'a',
'James Madison University Libraries is providing a metadata record and hyperlink to this full-text resource.',
'f', 'Unrestricted online access', '2', 'star'
])
field_506_2 = Field(tag='506',
indicators=['0', ' '],
subfields=[
'a', 'Open access content.', 'f',
'Open access content', '2', 'star'
])
field_540 = Field(
tag='540',
indicators=[' ', ' '],
subfields=[
'a',
'This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 License.',
'u',
'https://creativecommons.org/licenses/by-nc-nd/4.0/legalcode'
])
record = Record()
record.add_ordered_field(field_907)
record.add_ordered_field(field_024)
record.add_ordered_field(field_856)
record.add_ordered_field(field_506_1)
record.add_ordered_field(field_506_2)
record.add_ordered_field(field_540)
outmarc.write(record.as_marc())
outtext.write(oclcnum + '\n')
outsheet.write(i, 0, oclcnum)
outsheet.write(i, 1, j)
outsheet.write(i, 2, spreadsheet_024)
outsheet.write(i, 3, doi_url)
outbook.save('OCLC Changes.xls')
outmarc.close()
outtext.close()
def main(arglist):
parser = argparse.ArgumentParser()
parser.add_argument('input', help='path to spreadsheet')
# parser.add_argument('output', help='save directory')
args = parser.parse_args(arglist)
input = Path(args.input)
# Read spreadsheet
book_in = xlrd.open_workbook(str(input))
sheet = book_in.sheet_by_index(0) # get first sheet
col_headers = sheet.row_values(0)
title_col = col_headers.index('Title')
subj_person_col = col_headers.index('Subject_Person')
subj_topical_col = col_headers.index('Subject_Topical')
subj_place_col = col_headers.index('Subject_Place')
subj_corp_col = col_headers.index('Subject_Jurisdictional')
genre_col = col_headers.index('Genre')
pages_col = col_headers.index('Pages')
pub_date_col = col_headers.index('Date') # previously Publication Date
copy_date_col = col_headers.index('Copyright Date')
pub_place_col = col_headers.index('Pub_Place')
publisher_col = col_headers.index('Publisher')
edition_col = col_headers.index('Edition')
source_col = col_headers.index('Source')
# source_acq_col = col_headers.index('Source of Acquisition')
writer_col = col_headers.index('Writer')
penciller_col = col_headers.index('Penciller')
inker_col = col_headers.index('Inker')
colorist_col = col_headers.index('Colorist')
letterer_col = col_headers.index('Letterer')
cover_artist_col = col_headers.index('Cover Artist')
editor_col = col_headers.index('Editor')
# hist_note_col = col_headers.index('Historical Note')
notes_col = col_headers.index('Note')
characters_col = col_headers.index('Characters')
synopsis_col = col_headers.index('Story Arc')
toc_col = col_headers.index('Table of Contents')
in_series_col = col_headers.index('Is Part of Series')
black_creators_col = col_headers.index('Black Creators (MARC 590)')
black_chars_col = col_headers.index('Black Characters (MARC 590)')
isbn_col = col_headers.index('ISBN')
color_col = col_headers.index('Color?')
series_note_col = col_headers.index('Series Note')
copyright_holder_col = col_headers.index('Copyright holder')
gcd_uri_col = col_headers.index('Grand Comics Database')
outmarc = open('records.mrc', 'wb')
# Boilerplate fields
field_ldr = '00000nam a2200000Ii 4500'
field_040 = Field(tag = '040',
indicators = [' ',' '],
subfields = [
'a', 'VMC',
'b', 'eng',
'e', 'rda',
'c', 'VMC'])
field_049 = Field(tag = '049',
indicators = [' ',' '],
subfields = [
'a', 'VMCS'])
field_336_text = Field(tag = '336',
indicators = [' ',' '],
subfields = [
'a', 'text',
'b', 'txt',
'2', 'rdacontent'])
field_336_image = Field(tag = '336',
indicators = [' ',' '],
subfields = [
'a', 'still image',
'b', 'sti',
'2', 'rdacontent'])
field_337 = Field(tag = '337',
indicators = [' ',' '],
subfields = [
'a', 'unmediated',
'b', 'n',
'2', 'rdamedia'])
field_338 = Field(tag = '338',
indicators = [' ',' '],
subfields = [
'a', 'volume',
'b', 'nc',
'2', 'rdacarrier'])
field_380 = Field(tag = '380',
indicators = [' ',' '],
subfields = [
'a', 'Comic books and graphic novels.'])
field_506 = Field(tag = '506',
indicators = ['1',' '],
subfields = [
'a', 'Collection open to research. Researchers must register and agree to copyright and privacy laws before using this collection. Please contact Research Services staff before visiting the James Madison University Special Collections Library to use this collection.'])
field_542 = Field(tag = '542',
indicators = [' ',' '],
subfields = [
'a', 'Copyright not evaluated',
'u', 'http://rightsstatements.org/vocab/CNE/1.0/'])
field_588 = Field(tag = '588',
indicators = ['0',' '],
subfields = [
'a', 'Description based on indicia and Grand Comics Database.'])
field_989 = Field(tag = '989',
indicators = [' ',' '],
subfields = [
'a', 'PN6728'])
for row in range(1, sheet.nrows):
print('Record ' + str(row))
title = sheet.cell(row, title_col).value
print(title)
subj_person = sheet.cell(row, subj_person_col).value
if subj_person:
subj_person = [x.strip() for x in subj_person.split(';')]
subj_topical = sheet.cell(row, subj_topical_col).value
if subj_topical:
subj_topical = [x.strip() for x in subj_topical.split(';')]
subj_place = sheet.cell(row, subj_place_col).value
if subj_place:
subj_place = [x.strip() for x in subj_place.split(';')]
subj_corp = sheet.cell(row, subj_corp_col).value
if subj_corp:
subj_corp = [x.strip() for x in subj_corp.split(';')]
genre = sheet.cell(row, genre_col).value
genre = [x.strip() for x in genre.split(';')]
pages = str(sheet.cell(row, pages_col).value)
pub_date = str(sheet.cell(row, pub_date_col).value)
pub_date_str = date_from_string(pub_date)
pub_date_year = year_from_date(pub_date_str)
copy_date = ''
copy_date = str(sheet.cell(row, copy_date_col).value)
copy_date_str = date_from_string(copy_date)
copy_date_year = year_from_date(copy_date_str)
pub_place = sheet.cell(row, pub_place_col).value
publisher = sheet.cell(row, publisher_col).value
edition = sheet.cell(row, edition_col).value
source = sheet.cell(row, source_col).value
# source_acq = sheet.cell(row, source_acq_col).value
characters = sheet.cell(row, characters_col).value
black_creators = sheet.cell(row, black_creators_col).value
if black_creators:
black_creators = [x.strip() for x in black_creators.split(';')]
black_chars = sheet.cell(row, black_chars_col).value
if black_chars:
black_chars = [x.strip() for x in black_chars.split(';')]
isbn = str(sheet.cell(row, isbn_col).value)
color = sheet.cell(row, color_col).value
series_note = sheet.cell(row, series_note_col).value
gcd_uri = sheet.cell(row, gcd_uri_col).value
country_code = country_code_from_pub_place(pub_place)
copyright_holder = []
if sheet.cell(row, copyright_holder_col).value:
copyright_holder = sheet.cell(row, copyright_holder_col).value
copyright_holder = [x.strip() for x in copyright_holder.split(';')]
writer = []
if sheet.cell(row, writer_col).value:
writer = sheet.cell(row, writer_col).value
writer = [x.strip() for x in writer.split(';')]
penciller = []
if sheet.cell(row, penciller_col).value:
penciller = sheet.cell(row, penciller_col).value
penciller = [x.strip() for x in penciller.split(';')]
inker = []
if sheet.cell(row, inker_col).value:
inker = sheet.cell(row, inker_col).value
inker = [x.strip() for x in inker.split(';')]
colorist = []
if sheet.cell(row, colorist_col).value:
colorist = sheet.cell(row, colorist_col).value
colorist = [x.strip() for x in colorist.split(';')]
letterer = []
if sheet.cell(row, letterer_col).value:
letterer = sheet.cell(row, letterer_col).value
letterer = [x.strip() for x in letterer.split(';')]
cover_artist = []
if sheet.cell(row, cover_artist_col).value:
cover_artist = sheet.cell(row, cover_artist_col).value
cover_artist = [x.strip() for x in cover_artist.split(';')]
editor = []
if sheet.cell(row, editor_col).value:
editor = sheet.cell(row, editor_col).value
editor = [x.strip() for x in editor.split(';')]
# hist_note = []
# if sheet.cell(row, hist_note_col).value:
# hist_note = sheet.cell(row, hist_note_col).value
notes = []
if sheet.cell(row, notes_col).value:
notes = sheet.cell(row, notes_col).value
synopsis = []
if sheet.cell(row, synopsis_col).value:
synopsis = sheet.cell(row, synopsis_col).value
toc = []
if sheet.cell(row, toc_col).value:
toc = sheet.cell(row, toc_col).value
in_series = sheet.cell(row, in_series_col).value
contribs = {}
if copyright_holder:
for i in copyright_holder:
contribs.update({i: ['copyright holder']})
else:
if writer:
for i in writer:
contribs.update({i: ['writer']})
if penciller:
for i in penciller:
if i in contribs:
role_list = contribs[i]
role_list.append('penciller')
contribs.update({i: role_list})
else:
contribs.update({i: ['penciller']})
if inker:
for i in inker:
if i in contribs:
role_list = contribs[i]
role_list.append('inker')
contribs.update({i: role_list})
else:
contribs.update({i: ['inker']})
if colorist:
for i in colorist:
if i in contribs:
role_list = contribs[i]
role_list.append('colorist')
contribs.update({i: role_list})
else:
contribs.update({i: ['colorist']})
if letterer:
for i in letterer:
if i in contribs:
role_list = contribs[i]
role_list.append('letterer')
contribs.update({i: role_list})
else:
contribs.update({i: ['letterer']})
if cover_artist:
for i in cover_artist:
if i in contribs:
role_list = contribs[i]
role_list.append('cover artist')
contribs.update({i: role_list})
else:
contribs.update({i: ['cover artist']})
if editor:
for i in editor:
if i in contribs:
role_list = contribs[i]
role_list.append('editor')
contribs.update({i: role_list})
else:
contribs.update({i: ['editor']})
record = Record()
# Add boilerplate fields
record.leader = field_ldr
record.add_ordered_field(field_040)
record.add_ordered_field(field_049)
record.add_ordered_field(field_336_text)
record.add_ordered_field(field_336_image)
record.add_ordered_field(field_337)
record.add_ordered_field(field_338)
record.add_ordered_field(field_380)
record.add_ordered_field(field_506)
record.add_ordered_field(field_542)
record.add_ordered_field(field_588)
record.add_ordered_field(field_989)
# Add other fields
today = datetime.today().strftime('%y%m%d')
if copy_date:
data_008 = today + 't' + pub_date_year + copy_date_year + country_code + 'a 6 000 1 eng d'
else:
data_008 = today + 's' + pub_date_year + ' ' + country_code + 'a 6 000 1 eng d'
field_008 = Field(tag = '008',
data = data_008)
record.add_ordered_field(field_008)
if isbn:
field_020 = Field(tag = '020',
indicators = [' ',' '],
subfields = [
'a', isbn])
record.add_ordered_field(field_020)
subfields_099 = subfields_from_string(title)
if 'b' in subfields_099:
subfields_099.pop(3)
subfields_099.pop(2)
if 'n' in subfields_099:
subfields_099[subfields_099.index('n')] = 'a'
if subfields_099[1].endswith(',') or subfields_099[1].endswith(':'):
subfields_099[1] = subfields_099[1][:-1]
field_099 = Field(tag = '099',
indicators = [' ','9'],
subfields = subfields_099)
record.add_ordered_field(field_099)
for i in contribs:
if i == list(contribs.keys())[0] and 'copyright holder' in contribs[i]: # first contributor is copyright holder
subfield_content = subfields_from_string_relator(i, contribs[i])
field_110 = Field(tag = '110',
indicators = ['2', ' '],
subfields = subfield_content)
record.add_ordered_field(field_110)
elif i == list(contribs.keys())[0] and 'writer' in contribs[i]: # first contributor is a writer
subfield_content = subfields_from_string_relator(i, contribs[i])
field_100 = Field(tag = '100',
indicators = ['1', ' '],
subfields = subfield_content)
record.add_ordered_field(field_100)
else:
subfield_content = subfields_from_string_relator(i, contribs[i])
if ',' not in subfield_content[1]:
field_710 = Field(tag = '710',
indicators = ['2',' '],
subfields = subfield_content)
record.add_ordered_field(field_710)
else:
field_700 = Field(tag = '700',
indicators = ['1',' '],
subfields = subfield_content)
record.add_ordered_field(field_700)
if contribs and ('writer' in contribs[list(contribs.keys())[0]] or 'copyright holder' in contribs[list(contribs.keys())[0]]):
f245_ind1 = 1
else:
f245_ind1 = 0
f245_ind2 = 0
if str.startswith(title, 'The '):
f245_ind2 = 4
elif str.startswith(title, 'An '):
f245_ind2 = 3
elif str.startswith(title, 'A '):
f245_ind2 = 2
subfields_245 = subfields_from_string(title)
# If writer exists, add $c for first writer
if writer:
subfields_245[-1] = subfields_245[-1] + ' /'
subfields_245.append('c')
subfields_245.append(name_direct_order(subfields_from_string(writer[0])[1]) + ', writer.')
else:
# If no writer, add 245 ending punctuation
subfields_245[-1] = subfields_245[-1] + '.'
field_245 = Field(tag = '245',
indicators = [f245_ind1, f245_ind2],
subfields = subfields_245)
record.add_ordered_field(field_245)
if edition:
if not edition.endswith('.'):
edition += '.'
field_250 = Field(tag = '250',
indicators = [' ', ' '],
subfields = [
'a', edition])
record.add_ordered_field(field_250)
field_264_1 = Field(tag = '264',
indicators = [' ','1'],
subfields = [
'a', pub_place + ' :',
'b', publisher + ',',
'c', pub_date_str + '.'])
record.add_ordered_field(field_264_1)
if copy_date:
field_264_4 = Field(tag = '264',
indicators = [' ','4'],
subfields = [
'c', '©' + copy_date_str])
record.add_ordered_field(field_264_4)
if color == 'yes':
subfields_300 = [
'a', pages + ' pages :',
'b', 'chiefly color illustrations.']
elif color == 'no':
subfields_300 = [
'a', pages + ' pages :',
'b', 'black and white illustrations.']
field_300 = Field(tag = '300',
indicators = [' ',' '],
subfields = subfields_300)
record.add_ordered_field(field_300)
if title_to_series(title):
subfields_490 = title_to_series(title)
field_490 = Field(tag = '490',
indicators = ['1',' '],
subfields = subfields_490)
record.add_ordered_field(field_490)
if series_note:
if not series_note.endswith('.'):
series_note += '.'
field_490_series_note = Field(tag = '490',
indicators = ['1', ' '],
subfields = ['a', series_note])
record.add_ordered_field(field_490_series_note)
# if hist_note:
# field_500_hist = Field(tag = '500',
# indicators = [' ',' '],
# subfields = [
# 'a', hist_note + '.'])
# record.add_ordered_field(field_500_hist)
if notes:
field_500_notes = Field(tag = '500',
indicators = [' ',' '],
subfields = [
'a', notes + '.'])
record.add_ordered_field(field_500_notes)
if toc:
if not toc.endswith('.') and not toc.endswith('?') and not toc.endswith('!'):
toc += '.'
field_505 = Field(tag = '505',
indicators = ['0',' '],
subfields = [
'a', toc])
record.add_ordered_field(field_505)
if synopsis:
field_520 = Field(tag = '520',
indicators = [' ',' '],
subfields = [
'a', synopsis])
record.add_ordered_field(field_520)
if black_creators:
for i in black_creators:
if not i.endswith('.'):
i += '.'
field_590_creators = Field(tag = '590',
indicators = [' ',' '],
subfields = [
'a', i])
record.add_ordered_field(field_590_creators)
if black_chars:
for i in black_chars:
if not i.endswith('.'):
i += '.'
field_590_chars = Field(tag = '590',
indicators = [' ',' '],
subfields = [
'a', i])
record.add_ordered_field(field_590_chars)
if source:
field_541_source = Field(tag = '541',
indicators = [' ',' '],
subfields = [
'a', source + '.'])
record.add_ordered_field(field_541_source)
# if source_acq:
# field_541_source_acq = Field(tag = '541',
# indicators = [' ',' '],
# subfields = [
# 'a', source_acq + '.'])
# record.add_ordered_field(field_541_source_acq)
if subj_person:
for i in subj_person:
i_subfields = subfields_from_string(i)
# Set first indicator based on presence of comma in $a
if 'a' in i_subfields:
if ',' in i_subfields[i_subfields.index('a') + 1]:
field_600_ind1 = '1'
else:
field_600_ind1 = '0'
if '1' in i_subfields:
last_except_subf1 = i_subfields.index('1') - 1
else:
last_except_subf1 = len(i_subfields) - 1
if i_subfields[last_except_subf1].endswith(','):
i_subfields[last_except_subf1] = re.sub(r'^(.*),$', r'\g<1>.', i_subfields[last_except_subf1])
if not i_subfields[last_except_subf1].endswith('.') and not i_subfields[last_except_subf1].endswith(')') and not i_subfields[last_except_subf1].endswith('?') and not i_subfields[last_except_subf1].endswith('-'):
i_subfields[last_except_subf1] += '.'
field_600 = Field(tag = '600',
indicators = [field_600_ind1,'0'],
subfields = i_subfields)
record.add_ordered_field(field_600)
if subj_topical:
for i in subj_topical:
i_subfields = subfields_from_string(i)
if not i_subfields[-1].endswith('.') and not i_subfields[-1].endswith(')'):
i_subfields[-1] += '.'
field_650 = Field(tag = '650',
indicators = [' ','0'],
subfields = i_subfields)
record.add_ordered_field(field_650)
if subj_place:
for i in subj_place:
i_subfields = subfields_from_string(i)
if not i_subfields[-1].endswith('.') and not i_subfields[-1].endswith(')'):
i_subfields[-1] += '.'
field_651 = Field(tag = '651',
indicators = [' ','0'],
subfields = i_subfields)
record.add_ordered_field(field_651)
if subj_corp:
for i in subj_corp:
i_subfields = subfields_from_string(i)
if not i_subfields[-1].endswith('.') and not i_subfields[-1].endswith(')'):
i_subfields[-1] += '.'
field_610 = Field(tag = '610',
indicators = ['1','0'],
subfields = i_subfields)
record.add_ordered_field(field_610)
if genre:
for i in genre:
if not i.endswith('.') and not i.endswith(')'):
i += '.'
field_655 = Field(tag = '655',
indicators = [' ','7'],
subfields = [
'a', i,
'2', 'lcgft'])
record.add_ordered_field(field_655)
if characters:
field_500_chars = Field(tag = '500',
indicators = [' ', ' '],
subfields = [
'a', characters])
record.add_ordered_field(field_500_chars)
if gcd_uri:
title_758 = subfields_from_string(title)[1]
if title_758.endswith(',') or title_758.endswith(':'):
title_758 = title_758[:-1]
field_758 = Field(tag = '758',
indicators = [' ',' '],
subfields = [
'4', 'http://rdaregistry.info/Elements/m/P30135',
'i', 'Has work manifested:',
'a', title_758,
'1', gcd_uri])
record.add_ordered_field(field_758)
if in_series:
subfields_773 = subfields_from_string(in_series)
field_773 = Field(tag = '773',
indicators = ['0','8'],
subfields = subfields_773)
record.add_ordered_field(field_773)
subfields_852 = [
'b', 'CARRIER',
'c', 'carrspec']
if len(subfields_099) == 4:
subfields_852.append('h')
subfields_852.append(subfields_099[1])
subfields_852.append('i')
subfields_852.append(subfields_099[3])
if len(subfields_099) == 2:
subfields_852.append('h')
subfields_852.append(subfields_099[1])
if edition:
if edition.endswith('.'):
edition = edition[:-1]
subfields_852.append('z')
subfields_852.append(edition)
field_852 = Field(tag = '852',
indicators = ['8',' '],
subfields = subfields_852)
record.add_ordered_field(field_852)
outmarc.write(record.as_marc())
print()
outmarc.close()
def book_to_mark21_file(book,owner, xml = False):
#New record
record = Record()
# Number and value explanation : http://www.loc.gov/marc/bibliographic/bdleader.html
# Adding Leader tags
l = list(record.leader)
l[5] = 'n' # New
l[6] = 'a' #For manuscript file use 't'
l[7] = 'm' # Monograph
l[9] = 'a'
l[19] = '#'
record.leader = "".join(l)
# Category of material - Text
record.add_field(record_control_field('007','t'))
#Languages
languages = book.languages.all()
if languages:
for lang in languages:
record.add_field(record_control_field('008',lang.code))
else:
record.add_field(record_control_field('008','eng'))
#ISBN - International Standard Book Number
isbn = models.Identifier.objects.filter(book=book).exclude(identifier='pub_id').exclude(identifier='urn').exclude(identifier='doi')
for identifier in isbn:
if book.book_type:
record.add_field(record_field('020',['#','#'],['a', str(identifier.value)+' '+book.book_type]))
else:
record.add_field(record_field('020',['#','#'],['a', str(identifier.value)]))
#Source of acquisition
try:
base_url = models.Setting.objects.get(group__name='general', name='base_url').value
except:
base_url='localhost:8000'
book_url = 'http://%s/editor/submission/%s/' % (base_url, book.id)
record.add_field(record_field('030',['#','#'],['b', book_url]))
# Main entry - Personal name
authors = book.author.all()
author_names=''
for author in authors:
auhtor_names=author_names+author.full_name()+' '
name=author.last_name+', '+author.first_name
if author.middle_name:
name=name+' '+author.middle_name[:1]+'.'
record.add_field(record_field('100',['1','#'],['a', name]))
#Title statement
title_words = (book.title).split(' ')
first_word = title_words[0]
if first_word.lower() == 'the':
record.add_field(record_field('245',['1','4'],['a', book.title,'c',author_names]))
else:
record.add_field(record_field('245',['1','0'],['a', book.title,'c',author_names]))
#Publication
try:
press_name = models.Setting.objects.get(group__name='general', name='press_name').value
except:
press_name=None
try:
city = models.Setting.objects.get(group__name='general', name='city').value
except:
city = None
publication_info=[]
if book.publication_date:
#Press' city
if city :
publication_info.append('a')
publication_info.append(str(city))
#Press' name
if press_name:
publication_info.append('b')
publication_info.append(str(press_name))
#Date of Publication
publication_info.append('c')
publication_info.append(str(book.publication_date))
record.add_field(record_field('260',['#','#'],publication_info))
#Physical details
if book.pages:
record.add_field(record_field('300',['#','#'],['a',str(book.pages)+' pages']))
#Content type
record.add_field(record_field('336',['#','#'],['a', 'text','2','rdacontent']))
#Media type
record.add_field(record_field('337',['#','#'],['a', 'unmediated','2','rdamedia']))
#Carrier type
record.add_field(record_field('338',['#','#'],['a', 'volume','2','rdacarrier']))
#Language note
if languages:
for lang in languages:
record.add_field(record_field('546',['#','#'],['a', lang.display]))
else:
record.add_field(record_field('546',['#','#'],['a', 'In English']))
press_editors = book.press_editors.all()
#editors
for editor in press_editors:
record.add_field(record_field('700',['1','#'],['a', '%s, %s' % (editor.last_name,editor.first_name),'e','Press editor']))
#Series
if book.series:
record.add_field(record_field('830',['#','0'],['a', book.series.name ]))
if book.series.editor:
record.add_field(record_field('700',['1','#'],['a', '%s, %s' % (book.series.editor.last_name,book.series.editor.first_name),'e','Series editor']))
#Add record to file
title= book.title
if not xml:
filename='book_'+str(book.id)+'_'+re.sub('[^a-zA-Z0-9\n\.]', '', title.lower())+'_marc21.dat'
file=handle_marc21_file(record.as_marc(),filename, book, owner)
else:
filename='book_'+str(book.id)+'_'+re.sub('[^a-zA-Z0-9\n\.]', '', title.lower())+'_marc21.xml'
content=record_to_xml(record, quiet=False, namespace=False)
file=handle_marc21_file(content,filename, book, owner)
return file.pk
def write(self, record: Record) -> None:
"""Writes a record."""
Writer.write(self, record)
self.file_handle.write(record.as_marc())
rec_505 = Field(tag='505',
indicators=['0', ' '],
subfields=['a', toc])
new_marc_rec.add_ordered_field(rec_505)
#--------------------------------------------
# Create 520 field for the Abstract
abstract = fields[16].strip()
if not abstract == '':
rec_520 = Field(tag='520',
indicators=['3', ' '],
subfields=['a', abstract])
new_marc_rec.add_ordered_field(rec_520)
#--------------------------------------------
# Create 655 field for the Genre/Form term
# NOTE: if multiple terms are used in the field, you may want to try to break them up if they're separated by commas or other consistent punctuation
# Marked field as $2local since it may not be authorized term
genre = fields[17].strip()
if not genre == '':
rec_655 = Field(tag='655',
indicators=[' ', '7'],
subfields=['a', genre, '2', 'local'])
new_marc_rec.add_ordered_field(rec_655)
print 'After:'
print new_marc_rec
marc_recs_out.write(new_marc_rec.as_marc())
rec_cnt += 1
marc_recs_out.close()